© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12340
    Prev
    Next
    INDEX
    Explanations

    phrases involving avoidance or recommendations against certain actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens preceding "avoid" or its variations

    np_acts-logits-general · gemini-2.0-flash

    avoid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsTrue
    -0.33
     Incon
    -0.32
     medel
    -0.30
    outSlope
    -0.30
     McCullough
    -0.30
    ς
    -0.30
     Köz
    -0.28
    ổ
    -0.28
    WH
    -0.28
     HS
    -0.28
    POSITIVE LOGITS
     avoided
    2.56
     avoidance
    2.50
     avoid
    2.41
     avoiding
    2.38
    avoid
    2.34
    Avoid
    2.28
     avoids
    2.25
     Avoidance
    2.20
     Avoid
    2.20
     AVOID
    2.19
    Activations Density 0.410%

    No Known Activations